Add 8.0 link
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ Conversion was done using Evol-Instruct-Code-80k-v1.parquet as calibration datas
|
|
| 17 |
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
|
| 18 |
|
| 19 |
Original model: https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Download instructions
|
| 22 |
|
|
|
|
| 17 |
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
|
| 18 |
|
| 19 |
Original model: https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat
|
| 20 |
+
|
| 21 |
+
<a href="https://huggingface.co/bartowski/deepseek-llm-7b-chat-exl2/tree/8_0">8.0 bits per weight</a>
|
| 22 |
|
| 23 |
## Download instructions
|
| 24 |
|